Imputation of Medical Data Using Subspace Condition Order Degree Polynomials
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Temporal medical data is often collected during patient treatments thatrequire personal analysis. Each observation recorded in the temporal medical data isassociated with measurements and time treatments. A major problem in the analysis oftemporal medical data are the missing values that are caused, for example, by patientsdropping out of a study before completion. Therefore, the imputation of missing data isan important step during pre-processing and can provide useful information before thedata is mined. For each patient and each variable, this imputation replaces the missingdata with a value drawn from an estimated distribution of that variable. In this paper, wepropose a new method, called Newton’s finite divided difference polynomialinterpolation with condition order degree, for dealing with missing values in temporalmedical data related to obesity. We compared the new imputation method with threeexisting subspace estimation techniques, including the k-nearest neighbor, local leastsquares, and natural cubic spline approaches. The performance of each approach wasthen evaluated by using the normalized root mean square error and the statisticallysignificant test results. The experimental results have demonstrated that the proposedmethod provides the best fit with the smallest error and is more accurate than the other methods.
Abstract
Temporal medical data is often collected during patient treatments thatrequire personal analysis. Each observation recorded in the temporal medical data isassociated with measurements and time treatments. A major problem in the analysis oftemporal medical data are the missing values that are caused, for example, by patientsdropping out of a study before completion. Therefore, the imputation of missing data isan important step during pre-processing and can provide useful information before thedata is mined. For each patient and each variable, this imputation replaces the missingdata with a value drawn from an estimated distribution of that variable. In this paper, wepropose a new method, called Newton’s finite divided difference polynomialinterpolation with condition order degree, for dealing with missing values in temporalmedical data related to obesity. We compared the new imputation method with threeexisting subspace estimation techniques, including the k-nearest neighbor, local leastsquares, and natural cubic spline approaches. The performance of each approach wasthen evaluated by using the normalized root mean square error and the statisticallysignificant test results. The experimental results have demonstrated that the proposedmethod provides the best fit with the smallest error and is more accurate than the other methods.
참고문헌 (27)
- C. M. Antunes, "Temporal data mining: an overview", KDD 2001 Workshop on Temporal Data Mining (2001)
- X. Zhang, "Sequential local least squares imputation estimating missing value of microarray data", Computers in Biology and Medicine, 38(10), pp.1112~1120 (2008)
- A. R. Donders, "Review : a gentle introduction to imputation of missing values", J Clinical Epidemiology, 59(10), pp.1087~1091 (2006)
- A. Sahu, "Estimation methods for microarray data with missing values : a review", International Journal of Computer Science & Information Technologies, 2(2), pp.614~620 (2011)
- B. Mehala, "Selecting scalable algorithms to deal with missing values", International Journal of Recent Trends in Engineering, 1(2), pp.80~83 (2009)
- K. Raja, "Imputation framework for missing values", International Journal of Computer Trends and Technology, 3(2), pp.215~219 (2012)
- O. Troyanskaya, "Missing value estimation methods for DNA microarrays", Bioinformatics, 17(6), pp.520~525 (2001)
- J. F. Roddick, "A survey of temporal knowledge discovery paradigms and methods", IEEE Transactions on Knowledge and Data Engineering, 14(4), pp.750~767 (2002)
- M. H. Dunham, "Data Mining Introductory and Advanced Topics", pp.2003, Prentice Hall
- M. Dvornikov, "Spectral properties of numerical differentiation", Journal of Concrete and Applicable Mathematics, 6(1), pp.81~89 (2008)
- J. M. Jerez, "Missing data imputation in breast cancer prognosis", Proceedings of the 24th IASTED International Conference on Biomedical Engineering, pp.323~328 (2006)
- N. Viana, "Handling missing values in solar array performance degradation forecasting", Proceedings of the 15th Mini-EURO Conference on Managing Uncertainty in Decision Support Models (2004)
- D. N. Varsamis, "On a special case of the two-variable Newton interpolation polynomial", 2nd International Conference on Communications, Computing and Control Applications, pp.1~6 (2012)
- J. B. Scarborough, "Numerical Mathematical Analysis" (1966), Baltimore, Johns Hopkins Press
- K. E. Atkinson, "An Introduction to Numerical Analysis" (1989), Wiley
- M. N. Noraziana, "Estimation of missing values in air pollution data using single imputation techniques", ScienceAsia, 34(3), pp.341~345 (2008)
- S. Bose, "A novel interpolation based missing value estimation method to predict missing values in microarray gene expression data", International Conference on Communications, Devices and Intelligent Systems, pp.318~321 (2012)
- J. M. Jerez, "Missing data imputation using statistical and machine learning methods in a real breast cancer problem", Artificial Intelligence in Medicine, 50(2), pp.105~115 (2010)
- N. Eisemann, "Imputation of missing values of tumour stage in population-based cancer registration", BMC Medical Research Methodology, 11, pp.129~ (2011)
- S. Tsumoto, ""Rule discovery in large time-series medical databases," in Principles of Data Mining and Knowledge Discovery", Lecture Notes in Computer Science, 1704, pp.23~31 (1999), Springer Berlin
- E. Acuña, "Classification, Clustering, and Data Mining Applications", pp.639~647 (2004), Springer
- T. Cover, "Nearest neighbor pattern classification", IEEE Transactions on Information Theory, 13(1), pp.21~27 (1967)
- T. H. Bo, "LSimpute : accurate estimation of missing values in microarray data with least squares methods", Nucleic Acids Research, 32(3), pp.e34~ (2004)
- C. De Boor, "Applied Mathematical Sciences Volume 27" (1978), Springer-Verlag
- Cubic spline interpolation: a review, "G. Walberg", Department of Computer Science, Columbia University, ~, pp.Technical Report CUCS-389-88 (1988)
- B. Rosner, "The Wilcoxon signed rank test for paired comparisons of clustered data", Biometrics, 62(1), pp.185~192 (2006)
- M. Hollander, "Nonparametric Statistical Methods" (1973), Wiley